© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1483
    Prev
    Next
    INDEX
    Explanations

    Sanskrit characters and terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    410
    +0.10
    0.3%
    920
    +0.10
    0.3%
    1265
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.04
    1120
    +0.10
    0.03
    1871
    +0.09
    0.01
    Negative Logits
     ļ
    -1.54
     ieg
    -1.28
     izvē
    -1.26
     šķ
    -1.23
     pazi
    -1.21
     ģ
    -1.21
     nepiecieš
    -1.19
     vairāk
    -1.19
     ķ
    -1.13
     liel
    -1.03
    POSITIVE LOGITS
     shenan
    2.44
     hairc
    2.38
     eiffel
    2.26
     milf
    2.26
     affor
    2.25
     disagre
    2.23
     maneu
    2.21
     reluct
    2.19
     scrat
    2.14
     excru
    2.13
    Activations Density 0.324%

    No Known Activations